Print Email Facebook Twitter Federated learning: A comparison of methods Title Federated learning: A comparison of methods: How do different ML models compare to each other Author Sīpols, Emīls (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Garst, S.J.F. (mentor) Reinders, M.J.T. (graduation committee) Chen, Lydia Y. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2023-06-28 Abstract Federated learning (FL) has emerged as a promis-ing approach for training machine learning models using geographically distributed data. This paper presents a comprehensive comparative study of var-ious machine learning models in the context of FL. The aim is to evaluate the efficacy of these models in different data distribution scenarios and providepractical insights for practitioners in the field. The findings highlight the performance and limitations of linear and non-linear models on MNIST and Ki-nase datasets. Subject Machine LearningFederated LearningDistributed Machine Learning To reference this document use: http://resolver.tudelft.nl/uuid:5aaccd90-2079-4dd6-8d5f-4387ff9c1bdf Part of collection Student theses Document type bachelor thesis Rights © 2023 Emīls Sīpols Files PDF Final_paper_Emils.pdf 656.1 KB Close viewer /islandora/object/uuid:5aaccd90-2079-4dd6-8d5f-4387ff9c1bdf/datastream/OBJ/view